© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 98249
    Prev
    Next
    INDEX
    Explanations

    al

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idać
    -0.59
    SourceChecksum
    -0.58
     surla
    -0.57
     geral
    -0.57
    <bos>
    -0.57
    fromnode
    -0.54
    uyện
    -0.53
    upiter
    -0.52
    alnız
    -0.52
    ➞
    -0.52
    POSITIVE LOGITS
     Савезне
    0.64
    principalColumn
    0.56
    consulté
    0.54
     judiciales
    0.47
    Hozzáférés
    0.47
     sauvages
    0.47
     AppCompatTheme
    0.46
    Hochspringen
    0.46
    RegistryLite
    0.45
    GEBURTSDATUM
    0.45
    Activations Density 0.010%

    No Known Activations